基于驾驶人心理风险场模型的个性化换道决策方法

李珂; 韩同群; 杨正才; 高菲; 吴浩然

doi:10.3963/j.jssn.1674-4861.2023.06.004

基于驾驶人心理风险场模型的个性化换道决策方法

doi: 10.3963/j.jssn.1674-4861.2023.06.004

李珂^{1, 2,},
韩同群^{1, 2, ,},
杨正才^{1, 2},
高菲³,
吴浩然^{1, 2}

1.
湖北汽车工业学院汽车工程学院湖北十堰 442002
2.
湖北汽车工业学院汽车动力传动与电子控制湖北省重点实验室湖北十堰 442002
3.
吉林大学汽车仿真与控制国家重点实验室长春 130022

基金项目:

湖北省重点研发计划项目 2023BAB169

武汉市科技重大专项 2022013702025184

中央引导地方科技发展专项项目 2022BGE248

详细信息

作者简介:
李珂（1998—），硕士研究生. 研究方向：智能驾驶关键技术. E-mail: 2807070277@qq.com

通讯作者:
韩同群（1967—），硕士，教授. 研究方向：汽车动力系统仿真. E-mail: htqhtq67@sina.com

中图分类号: U491.25
计量
- 文章访问数: 149
- HTML全文浏览量: 41
- PDF下载量: 54
- 被引次数: 0
出版历程
- 收稿日期: 2023-05-04
- 网络出版日期: 2024-04-03

A Personalized Lane Change Decision Method Based on Driver's Psychological Risk Field Model

LI Ke^{1, 2
,},
HAN Tongqun^{1, 2
, ,},
YANG Zhengcai^{1, 2},
GAO Fei³,
WU Haoran^{1, 2}

1.
School of Automotive Engineering, Hubei University of Automotive Technology, Shiyan 442002, China
2.
Hubei Key Laboratory of Automotive Power Train and Electronic Control, Hubei University of Automotive Technology, Shiyan, 442002, China
3.
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China

摘要

摘要: 行驶环境中交互车辆的运动行为会对驾驶人心理产生刺激，引起驾驶人心理状态的变化，进而影响其换道决策行为。为此提出了1种基于驾驶人心理风险场模型的个性化换道决策方法。基于单向3车道快速路交通场景，通过交互式多模型分析车辆的横向速度与横向位移，引入可变横向速度相关的转移概率矩阵，预测交互车辆的目标车道选择；建立驾驶人心理风险场模型，量化行驶环境与交互车辆的运动行为对驾驶人心理风险造成的影响；利用高仿真驾驶模拟器联合SUMO试验平台开展287人次的模拟驾驶试验，通过建立混合交通仿真场景采集驾驶人的换道数据，并选取平均碰撞时间与驾驶人心理风险因子2个特征参数，使用K-means算法进行驾驶风格聚类，将驾驶人分为保守型、正常型和激进型这3类，并进一步确定不同风格的驾驶人在换道初始时刻所能接受的心理风险阈值。在此基础上，实现车辆的个性化安全换道决策。驾驶模拟器试验验证结果表明：对应于保守型、正常型和激进型的驾驶人，实际最小换道决策时间分别为3.48，6.29，11.33 s，实际最大换道决策时间分别为4.65，7.45，12.52 s，理论换道决策时间分别为4.09，6.83，11.95 s，所建立的换道决策模型的个性化换道时间预测误差均小于0.62 s。本方法可以准确评估不同风格驾驶人的心理风险，实现个性化的换道决策。
- 交通安全 /
- 换道决策 /
- 心理风险 /
- 驾驶风格 /
- 驾驶模拟
Abstract: In driving environments, the motion behavior of interacting vehicles can stimulate the psychological and mental state of drivers, subsequently influencing their lane-changing decision behavior. In response to this, a personalized lane-changing decision method based on a driver's psychological risk field model is investigated. Focusing on a three-lane expressway traffic scenario, the vehicles' lateral speed and lateral offset are analyzed by interacting multiple models. Variable lateral speed-related transition probability matrices are introduced to predict the target lane selection of interacting vehicles. A model is established to quantify the impact of the driving environment and interacting vehicles' motion behavior on drivers' psychological risk. The experiment is conducted by establishing mixed traffic scenarios in a SUMO-based driving simulator, and 287 cases of lane-change datasets are collected. Two characteristic parameters, average collision time and driver psychological risk factor, are selected. The K-means algorithm is used for driver style clustering, categorizing drivers into conservative, normal, and aggressive styles. Furthermore, different thresholds for psychological risk at the initial moment of lane-changing are determined for drivers with different styles. Then personalized safe lane-changing decisions for vehicles are implemented. Experimental results show that, for conservative, normal, and aggressive drivers, the actual minimum lane-changing decision times are 3.48, 6.29, and 11.33 s, respectively. The actual maximum lane-changing decision times are 4.65, 7.45, and 12.52 s, respectively. The theoretical lane-changing decision times are 4.09, 6.83, and 11.95 s, respectively. The prediction errors of the personalized lane-changing decision model are all less than 0.62 seconds. This approach accurately assesses the psychological risk of drivers with different styles and achieves personalized lane-changing decisions.
- traffic safety /
- lane-changing decision /
- psychological risk /
- driving style /
- driving simulation

HTML全文

图 1 换道决策方法路线图

Figure 1. Lane-changing decision method roadmap

下载: 全尺寸图片幻灯片

图 2 交互车辆运动行为预测模型结构图

Figure 2. Interactive vehicle motion behavior prediction model structure diagram

下载: 全尺寸图片幻灯片

图 3 转移概率矩阵的表示形式

Figure 3. Representation of transition probability matrix

下载: 全尺寸图片幻灯片

图 4 平均车速与每起事故平均死亡人数的关系

Figure 4. The relationship between average vehicle speed and the average number of deaths per accident

下载: 全尺寸图片幻灯片

图 5 单位事故损失与路面附着系数的关系

Figure 5. The relationship between unit accident loss and road surface friction coefficient

下载: 全尺寸图片幻灯片

图 6 驾驶模拟仿真环境

Figure 6. Driving simulation environment

下载: 全尺寸图片幻灯片

图 7 仿真场景图

Figure 7. Simulation scene graph

下载: 全尺寸图片幻灯片

图 8 驾驶风格分类

Figure 8. Driving style classification

下载: 全尺寸图片幻灯片

图 9 不同驾驶风格的驾驶人心理风险阈值

Figure 9. Psychological risk thresholds for drivers with different driving styles

下载: 全尺寸图片幻灯片

图 10 仿真场景示意图

Figure 10. Schematic diagram of simulation scenario

下载: 全尺寸图片幻灯片

图 11 目标车道预测概率变化（0~6 s）

Figure 11. Target lane prediction probability change(0~6 s)

下载: 全尺寸图片幻灯片

图 12 34名驾驶人的实际换道轨迹包络线

Figure 12. The actual lane change trajectory envelope for 34 drivers

下载: 全尺寸图片幻灯片

图 13 基于驾驶人心理风险的换道决策

Figure 13. Lane change decisions based on the driver's psychological risk

下载: 全尺寸图片幻灯片

表 1 中国5种类型道路安全交通事故数据

Table 1. Data on five type of road safety traffic accidents in China

道路类型	平均车速/（km/h）	死亡人数	平均死亡人数
高速公路	100	5 843	0.672
一级公路	70	6 532	0.359
二级公路	50	13 642	0.373
三级公路	35	7 499	0.327
四级公路	30	5 006	0.314

下载: 导出CSV

表 2 中国道路安全交通事故数据（路面状态）

Table 2. Chinese road safety traffic accident data (road surface status)

路面状态	路面附着系数	单位事故损失/（×1 000元）
干燥	0.90	4.978
潮湿	0.60	6.683
泥泞	0.55	6.438

下载: 导出CSV

表 3 不同道路线性的单位事故损失标定

Table 3. Unit accident loss calibration for different road linearities

道路曲率	道路坡度
道路曲率	平路	正常坡	陡坡	连续坡
直路	1.000	1.614	1.377	4.172
正常弯	1.174	1.425	1.540
急弯	1.256	1.274	1.412

下载: 导出CSV

表 4 不同驾龄驾驶人的心理风险标定

Table 4. Psychological risk calibration for drivers of different driving experience

编号	驾龄u/年	ψ(de)
1	＞0~1	0.601
2	＞1~2	0.612
3	＞2~3	0.685
4	＞3~4	0.672
5	＞4~5	0.668
6	＞5~10	0.795
7	＞10~15	0.921
8	＞15~20	0.947
9	＞20	1.000

下载: 导出CSV

表 5 不同受教育程度驾驶人的心理风险标定

Table 5. Psychological risk calibration for drivers with different levels of education

编号	受教育程度	ψ(rt)
1	无	0.690
2	小学	0.458
3	中学	0.372
4	本科	1.000
5	本科以上	0.786

下载: 导出CSV

表 6 不同驾驶风格的驾驶人心理风险阈值

Table 6. Psychological risk thresholds for drivers with different driving styles

驾驶风格	K_α	K_β
保守型	0.109 9	0.179 7
正常型	0.152 0	0.378 4
激进型	0.290 4	0.677 5

下载: 导出CSV

表 7 不同驾驶风格的换道轨迹决策时间

Table 7. Lane change trajectory decision times for different driving styles

驾驶风格	换道决策时间/s
驾驶风格	最小值	最大值
保守型	3.48	4.65
正常型	6.29	7.45
激进型	11.33	12.52

下载: 导出CSV

参考文献(26)

[1]	LI Q W, LI X P, MANNERING F. Assessment of discretionary lane-changing decisions using a random parameters approach with heterogeneity in means and variances[J]. Transportation Research Record, 2021 (6): 330-338.
[2]	GIPPS P G. A model for the structure of lane-changing decisions[J]. Transportation Research Part B: Methodological, 1986, 20 (5): 403-414. doi: 10.1016/0191-2615(86)90012-3
[3]	王慧然, 陈无畏, 王其东, 等. 基于相邻车道安全态势划分的换道决策[J]. 机械工程学报, 2023, 59 (2): 233-244. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202302020.htm WANG H R, CHEN W W, WANG Q D, et al. Lane change decision based on the safety state division of the adjacent lanes[J]. Journal of Mechanical Engineering, 2023, 59(2): 233-244. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202302020.htm
[4]	WANG J J, ZHANG Q C, ZHAO D B, et al. Lane change decision-making through deep reinforcement learning with rule-based constraints[C]. 2019 International Joint Conference on Neural Networks(IJCNN), Budapest, Hungary : IEEE, 2019.
[5]	SHENG Z H, LIU L, XUE S B, et al. A cooperation-aware lane change method for autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 24(3): 3236-3251.
[6]	WANG W D, QIE T Q, YANG C, et al. An intelligent lane-changing behavior prediction and decision-making strategy for an autonomous vehicle[J]. IEEE Transactions on Industrial Electronics, 2021, 69 (3): 2927-2937.
[7]	SATHYAN A, MA J Q, COHEN K. Decentralized cooperative driving automation: a reinforcement learning framework using genetic fuzzy systems[J]. Transportmetrica B: Transport Dynamics, 2021, 9 (1): 775-797. doi: 10.1080/21680566.2021.1951394
[8]	聂琳真, 管家意, 卢炽华, 等. 基于模糊逻辑的高速公路微观换道行为[J]. 北京工业大学学报, 2018, 44 (3): 424-432. https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD201803015.htm NIE L Z, GUAN J Y, LU C H, et al. Micro-lane changing behavior of expressways based on fuzzy logic[J]. Journal of Beijing University of Technology, 2018, 44(3): 424-432. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD201803015.htm
[9]	GU X P, HAN Y P, YU J F. A novel lane-changing decision model for autonomous vehicles based on deep autoencoder network and XGBoost[J]. IEEE Access, 2020, (8) : 9846-9863.
[10]	FAN B, WU Y, HE Z B, et al. Digital twin empowered mobile edge computing for intelligent vehicular lane-changing[J]. IEEE Network, 2021, 35 (6): 194-201. doi: 10.1109/MNET.201.2000768
[11]	CHENG S, YANG B, WANG Z, et al. Spatio-temporal image representation and deep-learning-based decision framework for automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23 (12): 24866-24875. doi: 10.1109/TITS.2022.3195213
[12]	ZHOU W, CHEN D, YAN J, et al. Multi-agent reinforcement learning for cooperative lane changing of connected and autonomous vehicles in mixed traffic[J]. Autonomous Intelligent Systems, 2022, 2 (1): 1-11. doi: 10.1007/s43684-021-00019-7
[13]	ZHANG X H, SUN J, QI X, et al. Simultaneous modeling of car-following and lane-changing behaviors using deep learning[J]. Transportation Research Part C: Emerging Technologies, 2019 (104): 287-304.
[14]	XIE D F, FANG Z Z, JIA B, et al. A data-driven lane-changing model based on deep learning[J]. Transportation Research Part C: Emerging Technologies, 2019, (106): 41-60.
[15]	GAO J, MURPHEY Y L, ZHU H H. Multivariate time series prediction of lane changing behavior using deep neural network[J]. Applied Intelligence, 2018, 48 (10): 3523-3537.
[16]	WANG X Y, GUO Y Q, BAI C L, et al. Driver's intention identification with the involvement of emotional factors in two-lane roads[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22 (11): 6866-6874.
[17]	LIU Y Q, WANG X Y. The analysis of driver's behavioral tendency under different emotional states based on a Bayesian Network[J]. IEEE Transactions on Affective Computing, 2020, 14 (1): 165-177.
[18]	LING J, LI J, TEI K, et al. Towards personalized autonomous driving: an emotion preference style adaptation framework[C]. 2021 IEEE International Conference on Agents (ICA), Kyoto, Japan: IEEE, 2021.
[19]	李青, 景云超, 朱彤, 等. 基于LightGBM的驾驶人风险感知能力判别方法[J]. 交通信息与安全, 2021, 39 (4): 16-25. doi: 10.3963/j.jssn.1674-4861.2021.04.003 LI Q, JING Y C, ZHU T, et al. Driver risk perception ability identification method based on LightGBM[J]. Journal of Transport Information and Safety, 2021, 39(4): 16-25. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2021.04.003
[20]	GAO H B, QIN Y C, HU C, et al. An interacting multiple model for trajectory prediction of intelligent vehicles in typical road traffic scenario[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34 (9): 1-12.
[21]	PAK J M. Hybrid interacting multiple model filtering for improving the reliability of radar-based forward collision warning systems[J]. Sensors, 2022, 22 (3): 875.
[22]	GOMAA M A K, DE SILVA O, MANN G K I, et al. Observability-constrained VINS for MAVs using interacting multiple model algorithm[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 57 (3): 1423-1442.
[23]	FAN X X, WANG G, HAN J C, et al. Interacting multiple model based on maximum correntropy Kalman filter[J]. IEEE Transactions on Circuits and Systems Ⅱ: Express Briefs, 2021, 68 (8): 3017-3021.
[24]	LI Y, WANG J Q, WU J. Model calibration concerning risk coefficients of driving safety field model[J]. Journal of Central South University, 2017, 24 (6): 1494-1502.
[25]	郭子彬, 陈慧, 夏韬锴, 等. 弯道工况下驾驶人主观风险感知的量化研究[J]. 汽车工程, 2022, 44 (9): 1447-1455. GUO Z B, CHEN H, XIA T K, et al. Quantitative study of driver's subjective risk perceptionunder curved working conditions[J]. Automotive Engineering, 2022, 44(9): 1447-1455. (in Chinese)
[26]	公安部交通管理局. 中国道路交通事故统计年报[R]. 北京: 公安部交通管理局, 2017. Ministry of Public Security, Transportation Bureau. The road traffic accidents statistics report in China[R]. Beijing: Ministry of Public Security, Transportation Bureau, 2017. (in Chinese)